test push

config.json

@@ -0,0 +1,52 @@
+{
+  "architectures": [
+    "LlamaButlerForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_reduce_factor": 8,
+  "auto_map": {
+    "AutoConfig": "modeling_llama_butler:LlamaButlerConfig",
+    "AutoModel": "modeling_llama_butler:LlamaButlerForCausalLM",
+    "AutoModelForCausalLM": "modeling_llama_butler:LlamaButlerForCausalLM"
+  },
+  "bos_token_id": 128000,
+  "dDash": 32,
+  "eos_token_id": 128001,
+  "eval_llm_mode": "ExpPred",
+  "flash_attn": false,
+  "head_attn_reduce_factor": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intdim": 1024,
+  "intermediate_size": 14336,
+  "lookahead": 0,
+  "max_position_embeddings": 131072,
+  "min_sparse_index": 8,
+  "mlp_bias": false,
+  "model_type": "llama_butler",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "producer_frequency": 32,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "sliding_window": 128,
+  "tie_word_embeddings": false,
+  "token_sparse_method": "fixed_50pc",
+  "torch_dtype": "float32",
+  "train_headpredictor": false,
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}